Computer Vision Introduction

1. Staff
Web Page
• http://www.cs.washington.edu/education/courses/cse576/08sp/
Handouts
• signup sheet
• intro slides
• image filtering slides
Computer Vision (CSE 576)
Steve Seitz
seitz@cs.washington.edu
Rick Szeliski
szeliski@microsoft.com
TA: Jiun-Hung Chen
jhchen@cs.washington.edu

2. Today
• Intros
• Computer vision overview
• Course overview
• Image processing
Readings
• Book: Richard Szeliski, Computer Vision: Algorithms and Applications
– (please check Web site weekly for updated drafts)
– Intro: Ch 1.0

3. What is computer vision?

4. What is computer vision?
Terminator 2

5. Every picture tells a story
Goal of computer vision is to write computer programs
that can interpret images

6. Can computers match (or beat) human vision?
Yes and no (but mostly no!)
• humans are much better at “hard” things
• computers can be better at “easy” things

7. Human perception has its shortcomings…
Sinha and Poggio, Nature, 1996

8. Copyright A.Kitaoka 2003

9. Current state of the art
The next slides show some examples of what
current vision systems can do

10. Earth viewers (3D modeling)
Image from Microsoft’s Virtual Earth
(see also: Google Earth)

11. Photosynth
http://labs.live.com/photosynth/
Based on Photo Tourism technology developed here in CSE!
by Noah Snavely, Steve Seitz, and Rick Szeliski

12. Optical character recognition (OCR)
Digit recognition, AT&T labs
http://www.research.att.com/~yann/
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software
License plate readers
http://en.wikipedia.org/wiki/Automatic_number_plate_recognition

13. Face detection
Many new digital cameras now detect faces
• Canon, Sony, Fuji, …

14. Smile detection?
Sony Cyber-shot® T70 Digital Still Camera

15. Object recognition (in supermarkets)
LaneHawk by EvolutionRobotics
“A smart camera is flush-mounted in the checkout lane, continuously watching
for items. When an item is detected and recognized, the cashier verifies the
quantity of items that were found under the basket, and continues to close the
transaction. The item can remain under the basket, and with LaneHawk,you are
assured to get paid for it… “

16. Face recognition
Who is she?

17. Vision-based biometrics
“How the Afghan Girl was Identified by Her Iris Patterns” Read the story

18. Login without a password…
Fingerprint scanners on
many new laptops,
other devices
Face recognition systems now
beginning to appear more widely
http://www.sensiblevision.com/

19. Object recognition (in mobile phones)
This is becoming real:
• Microsoft Research
• Point & Find, Nokia

20. The Matrix movies, ESC Entertainment, XYZRGB, NRC
Special effects: shape capture

21. Pirates of the Carribean, Industrial Light and Magic
Click here for interactive demo
Special effects: motion capture

22. Sports
Sportvision first down line
Nice explanation on www.howstuffworks.com

23. Smart cars
Mobileye
• Vision systems currently in high-end BMW, GM, Volvo models
• By 2010: 70% of car manufacturers.
• Video demo
Slide content courtesy of Amnon Shashua

24. Vision-based interaction (and games)
Nintendo Wii has camera-based IR
tracking built in. See Lee’s work at
CMU on clever tricks on using it to
create a multi-touch display!
Digimask: put your face on a 3D avatar.
“Game turns moviegoers into Human Joysticks”, CNET
Camera tracking a crowd, based on this work.

25. Vision in space
Vision systems (JPL) used for several tasks
• Panorama stitching
• 3D terrain modeling
• Obstacle detection, position tracking
• For more, read “Computer Vision on Mars” by Matthies et al.
NASA'S Mars Exploration Rover Spirit captured this westward view from atop
a low plateau where Spirit spent the closing months of 2007.

26. Robotics
http://www.robocup.org/
NASA’s Mars Spirit Rover
http://en.wikipedia.org/wiki/Spirit_rover

27. Medical imaging
Image guided surgery
Grimson et al., MIT
3D imaging
MRI, CT

28. Current state of the art
You just saw examples of current systems.
• Many of these are less than 5 years old
This is a very active research area, and rapidly changing
• Many new apps in the next 5 years
To learn more about vision applications and companies
• David Lowe maintains an excellent overview of vision
companies
– http://www.cs.ubc.ca/spider/lowe/vision.html

29. This course
http://www.cs.washington.edu/education/courses/cse576/08sp/

30. Project 1: features

31. Project 2: panorama stitching
http://www.cs.washington.edu/education/courses/cse576/05sp/projects/proj2/artifacts/winners.html
Indri Atmosukarto, 576 08sp

32. Project 3: Face Recognition

33. Final Project
Open-ended project of your choosing
(in teams of two)

34. Grading
Based on projects
No midterm or final

35. General Comments
Prerequisites—these are essential!
• Data structures
• A good working knowledge of C and C++ programming
– (or willingness/time to pick it up quickly!)
• Linear algebra
• Vector calculus
Course does not assume prior imaging experience
• computer vision, image processing, graphics, etc.